Feasibility of multi-atlas cardiac segmentation from thoracic planning CT in a probabilistic framework

Toxicity to cardiac and coronary structures is an important late morbidity for patients undergoing left-sided breast radiotherapy. Many current studies have relied on estimates of cardiac doses assuming standardised anatomy, with a calculated increase in relative risk of 7.4% per Gy (mean heart dose). To provide individualised estimates for dose, delineation of various cardiac structures on patient images is required. Automatic multi-atlas based segmentation can provide a consistent, robust solution, however there are challenges to this method. We are aiming to develop and validate a cardiac atlas and segmentation framework, with a focus on the limitations and uncertainties in the process. We present a probabilistic approach to segmentation, which provides a simple method to incorporate inter-observer variation, as well as a useful tool for evaluating the accuracy and sources of error in segmentation. A dataset consisting of 20 planning computed tomography (CT) images of Australian breast cancer patients with delineations of 17 structures (including whole heart, four chambers, coronary arteries and valves) was manually contoured by three independent observers, following a protocol based on a published reference atlas, with verification by a cardiologist. To develop and validate the segmentation framework a leave-one-out cross-validation strategy was implemented. Performance of the automatic segmentations was evaluated relative to inter-observer variability in manually-derived contours; measures of volume and surface accuracy (Dice similarity coefficient (DSC) and mean absolute surface distance (MASD), respectively) were used to compare automatic segmentation to the consensus segmentation from manual contours. For the whole heart, the resulting segmentation achieved a DSC of [Formula: see text], with a MASD of [Formula: see text] mm. Quantitative results, together with the analysis of probabilistic labelling, indicate the feasibility of accurate and consistent segmentation of larger structures, whereas this is not the case for many smaller structures, where a major limitation in segmentation accuracy is the inter-observer variability in manual contouring.

[1]  T van Walsum,et al.  Evaluation of a multi-atlas based method for segmentation of cardiac CTA data: a large-scale, multicenter, and multivendor study. , 2010, Medical physics.

[2]  Tom Vercauteren,et al.  An ITK Implementation of the Symmetric Log-Domain Diffeomorphic Demons Algorithm , 2009, The Insight Journal.

[3]  Daniel Rueckert,et al.  Nonrigid registration using free-form deformations: application to breast MR images , 1999, IEEE Transactions on Medical Imaging.

[4]  Torsten Rohlfing,et al.  Performance-based classifier combination in atlas-based image segmentation using expectation-maximization parameter estimation , 2004, IEEE Transactions on Medical Imaging.

[5]  Daniel Gomez,et al.  Automatic segmentation of cardiac substructures from noncontrast CT images: accurate enough for dosimetric analysis? , 2018, Acta oncologica.

[6]  Mert R. Sabuncu,et al.  Multi-atlas segmentation of biomedical images: A survey , 2014, Medical Image Anal..

[7]  Simon R. Arridge,et al.  An Atlas-Based Segmentation Propagation Framework Using Locally Affine Registration - Application to Automatic Whole Heart Segmentation , 2008, MICCAI.

[8]  Arrate Muñoz-Barrutia,et al.  Efficient classifier generation and weighted voting for atlas-based segmentation: two small steps faster and closer to the combination oracle , 2008, SPIE Medical Imaging.

[9]  Daniel Rueckert,et al.  Automatic anatomical brain MRI segmentation combining label propagation and decision fusion , 2006, NeuroImage.

[10]  Zhe Wang,et al.  Exposure of the Heart in Breast Cancer Radiation Therapy: A Systematic Review of Heart Doses Published During 2003 to 2013. , 2015, International journal of radiation oncology, biology, physics.

[11]  Ludmila I. Kuncheva,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2004 .

[12]  Aamer Chughtai,et al.  Development and validation of a heart atlas to study cardiac exposure to radiation following treatment for breast cancer. , 2011, International journal of radiation oncology, biology, physics.

[13]  Jason A. Dowling,et al.  Atlas-based segmentation technique incorporating inter-observer delineation uncertainty for whole breast , 2017 .

[14]  Carsten Brink,et al.  Automatic segmentation of the heart in radiotherapy for breast cancer , 2014, Acta oncologica.

[15]  R. Peto,et al.  Long-term mortality from heart disease and lung cancer after radiotherapy for early breast cancer: prospective cohort study of about 300,000 women in US SEER cancer registries. , 2005, The Lancet. Oncology.

[16]  Luis Ibáñez,et al.  The Design of SimpleITK , 2013, Front. Neuroinform..

[17]  Torsten Rohlfing,et al.  Quo Vadis, Atlas-Based Segmentation? , 2005 .

[18]  Pierre Soille,et al.  Morphological Image Analysis , 1999 .

[19]  Radhe Mohan,et al.  Implementation and validation of a three-dimensional deformable registration algorithm for targeted prostate cancer radiotherapy. , 2004, International journal of radiation oncology, biology, physics.

[20]  Yu Cao,et al.  Multi-atlas Segmentation with Learning-Based Label Fusion , 2014, MLMI.

[21]  D. Louis Collins,et al.  Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation , 2011, NeuroImage.

[22]  Joseph O. Deasy,et al.  Succesful Implementation of Atlas Segmentation for Cardiac Substructures , 2017 .

[23]  Mohammad Hedayati,et al.  Chloroquine improves survival and hematopoietic recovery after lethal low-dose-rate radiation. , 2012, International journal of radiation oncology, biology, physics.

[24]  H. Mouridsen,et al.  [Danish Breast Cancer Cooperative Group]. , 2012, Ugeskrift for laeger.

[25]  Wiro J Niessen,et al.  Automatic segmentation and quantification of the cardiac structures from non-contrast-enhanced cardiac CT scans , 2017, Physics in medicine and biology.

[26]  David R. Haynor,et al.  Nonrigid multimodality image registration , 2001, SPIE Medical Imaging.

[27]  Josien P W Pluim,et al.  Multiatlas-based segmentation with preregistration atlas selection. , 2013, Medical physics.

[28]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[29]  Torsten Rohlfing,et al.  Evaluation of atlas selection strategies for atlas-based image segmentation with application to confocal microscopy images of bee brains , 2004, NeuroImage.

[30]  William M. Wells,et al.  Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation , 2004, IEEE Transactions on Medical Imaging.

[31]  Carsten Brink,et al.  Automatic segmentation of heart evaluated with multi-instiution inter-observer variation , 2012 .

[32]  Max A. Viergever,et al.  Multi-Atlas-Based Segmentation With Local Decision Fusion—Application to Cardiac and Aortic Segmentation in CT Scans , 2009, IEEE Transactions on Medical Imaging.

[33]  Daniel Rueckert,et al.  Multi-atlas based segmentation of brain images: Atlas selection and its effect on accuracy , 2009, NeuroImage.

[34]  Daniel Rueckert,et al.  Multiatlas whole heart segmentation of CT data using conditional entropy for atlas ranking and selection. , 2015, Medical physics.

[35]  H. Bartelink,et al.  Long-term risk of cardiovascular disease in 10-year survivors of breast cancer. , 2007, Journal of the National Cancer Institute.

[36]  P. Hall,et al.  Risk of ischemic heart disease in women after radiotherapy for breast cancer. , 2013, The New England journal of medicine.

[37]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[38]  Nicholas Ayache,et al.  Unifying maximum likelihood approaches in medical image registration , 2000 .

[39]  Max A. Viergever,et al.  elastix: A Toolbox for Intensity-Based Medical Image Registration , 2010, IEEE Transactions on Medical Imaging.

[40]  Sébastien Ourselin,et al.  A Registration-Based Propagation Framework for Automatic Whole Heart Segmentation of Cardiac MRI , 2010, IEEE Transactions on Medical Imaging.

[41]  Sébastien Ourselin,et al.  STEPS: Similarity and Truth Estimation for Propagated Segmentations and its application to hippocampal segmentation and brain parcelation , 2013, Medical Image Anal..

[42]  Carsten Brink,et al.  Uncertainties in estimating heart doses from 2D-tangential breast cancer radiotherapy , 2016, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[43]  Michael J Ackerman,et al.  Engineering and algorithm design for an image processing Api: a technical report on ITK--the Insight Toolkit. , 2002, Studies in health technology and informatics.

[44]  Tinsu Pan,et al.  Cardiac atlas development and validation for automatic segmentation of cardiac substructures. , 2017, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[45]  R Peto,et al.  Effect of radiotherapy after breast-conserving surgery on 10-year recurrence and 15-year breast cancer death: meta-analysis of individual patient data for 10 801 women in 17 randomised trials , 2011, The Lancet.

[46]  Jacques Bernier,et al.  Radiotherapy in DCIS, an underestimated benefit? , 2014, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[47]  Carlos Ortiz-de-Solorzano,et al.  Combination Strategies in Multi-Atlas Image Segmentation: Application to Brain MR Data , 2009, IEEE Transactions on Medical Imaging.

[48]  Simon K. Warfield,et al.  Simultaneous Truth and Performance Level Estimation Through Fusion of Probabilistic Segmentations , 2013, IEEE Transactions on Medical Imaging.

[49]  Vincenzo Valentini,et al.  Recommendations on how to establish evidence from auto-segmentation software in radiotherapy. , 2014, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[50]  Nicholas Ayache,et al.  Symmetric Log-Domain Diffeomorphic Registration: A Demons-Based Approach , 2008, MICCAI.

[51]  Bennett A Landman,et al.  Non-local statistical label fusion for multi-atlas segmentation , 2013, Medical Image Anal..

[52]  Max A. Viergever,et al.  Adaptive local multi-atlas segmentation: Application to the heart and the caudate nucleus , 2010, Medical Image Anal..

[53]  Gang Liu,et al.  Label fusion for segmentation via patch based on local weighted voting , 2017, Frontiers of Information Technology & Electronic Engineering.